SOURCE-LINKED INTELLIGENCE

Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Multimodal model merging aims to consolidate task experts into a single model that retains their complementary capabilities. Most unimodal model merging methods combine expert updates within individual layers, and multimodal approaches largely follow this design. However, an expert update changes the representations passed to subsequent layers, allowing its influence to propagate across depth and affect how visual and textual information interact. When visual and language updates are combined, later updates act on inputs already modified by earlier ones, coupling their effects. This poses two

Read original source ↗ Open in workspace

recordType

paper

region

Global